Grid-based local feature bundling for efficient object search and localization
Date of Issue2011
IEEE International Conference on Image Processing (18th : 2011 : Brussels, Belgium)
School of Electrical and Electronic Engineering
We propose a new grid-based image representation for dis- criminative visual object search, with the goal to efficiently locate the query object in a large image collection. After ex- tracting local invariant features, we partition the image into non-overlapped rectangular grid cells. Each grid bundles the local features within it and is characterized by a histogram of visual words. Given both positive and negative queries, each grid is assigned a mutual information score to match and lo- cate the query object. This new image representation brings in two great benefits for efficient object search: 1) as the grid bundles local features, the spatial contextual information en- hances the discriminative matching; and 2) it enables faster object localization by searching visual object on the grid-level image. To evaluate our approach, we perform experiments on a very challenging logo database BelgaLogos  of 10,000 images. The comparison with the state-of-the-art methods highlights the effectiveness of our approach in both accuracy and speed.
DRNTU::Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision
© 2011 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: http://dx.doi.org/10.1109/ICIP.2011.6115629.